Update README.md
Browse filesUpdating long context section after confirming coherence at 64K context
README.md
CHANGED
|
@@ -22,7 +22,7 @@ This model was designed for roleplaying and storytelling and I think it does wel
|
|
| 22 |
|
| 23 |
### Long Context Tips
|
| 24 |
|
| 25 |
-
You can run this model out to 32K context with alpha_rope set to 1, just like with Miqu. Enjoy!
|
| 26 |
|
| 27 |
### Sampler Tips
|
| 28 |
|
|
|
|
| 22 |
|
| 23 |
### Long Context Tips
|
| 24 |
|
| 25 |
+
You can run this model out to 32K context with alpha_rope set to 1, just like with Miqu. Limited testing shows coherence out to 64K using alpha_rope 2.5. Enjoy!
|
| 26 |
|
| 27 |
### Sampler Tips
|
| 28 |
|